「train」の検索結果

AgentDB Reinforcement Learning Training operates on 3 fundamental principles:

日本語の概要は準備中です。原文の説明を表示しています。

Write or rewrite prose so it sounds like a human wrote it — not a frontier model. Named in homage to Rabindranath Tagore, whose prose carried what frontier models reach for and miss: a point of view, specificity over abstraction, and restraint over puffery. Merges two complementary approaches: a 29-pattern catalog of AI tells (from humanizer) plus an 8-rule operating system with an 8-dimension scoring gate (extending stop-slop). Use when drafting, editing, or reviewing any prose: essays, posts, docs, reports, emails. Detects and removes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary, passive voice, negative parallelisms, filler phrases, inanimate-verb constructions, narrator-from-a-distance voice, and metronomic rhythm. Adds back the things AI writing usually lacks: point of view, stakes, specificity, restraint, varied rhythm, and trust in the reader.

日本語の概要は準備中です。原文の説明を表示しています。

Assemble the human genetic evidence for and against a target before a programme commits to it — the evidence class that most improves the odds of surviving clinical development. Use this skill to pull gnomAD constraint metrics (LOEUF, pLI, observed/expected) that show whether loss of function is tolerated in people, retrieve GWAS Catalog associations and fine-mapped credible sets for a gene, and read a natural human knockout as a safety readout. Also trigger on gnomAD, LOEUF, pLI, loss-of-function intolerance, mutational constraint, GWAS Catalog, credible set, human knockout, genetic support, or target safety dossier.

日本語の概要は準備中です。原文の説明を表示しています。

Molecular featurization hub with one consistent interface over 100+ featurizers. Fingerprints (ECFP/Morgan, MACCS, atom pair, topological torsion, Avalon, RDKit, ERG), RDKit and Mordred descriptor sets, pharmacophore and 3D shape descriptors, scaffold keys, and pretrained embeddings (ChemBERTa, ChemGPT, MolT5, GIN, Graphormer) through a common transformer API with caching and parallelism. Use this skill to convert SMILES into model-ready feature matrices for QSAR, virtual screening, and molecular ML, and to choose between featurizer families. Also trigger on molfeat, MoleculeTransformer, FPVecTransformer, PretrainedHFTransformer, molfeat model store, or featurizer selection.

日本語の概要は準備中です。原文の説明を表示しています。

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For ready-made ADMET numbers without training a model use admet-prediction; for benchmark datasets and task-aware splits use pytdc.

日本語の概要は準備中です。原文の説明を表示しています。

Cofold protein-ligand, protein-protein, and nucleic-acid complexes with Boltz-2, and predict binding affinity with its trained affinity head. Use this skill to build Boltz input YAML, run structure prediction with MSAs, pocket constraints, templates, and modified residues, screen compound libraries by cofolding, and interpret confidence scores (pLDDT, pTM, ipTM, PDE) and affinity output (binder probability and log10 IC50). Also trigger on Boltz, Boltz-1, Boltz-2, cofolding, boltz predict, affinity_pred_value, affinity_probability_binary, ipTM, or open-weights AlphaFold3 alternatives.

日本語の概要は準備中です。原文の説明を表示しています。

Register trained models in MLflow Model Registry with version control, implement stage transitions (Staging, Production, Archived) with approval workflows, and manage model lineage with comprehensive metadata and deployment tracking. Use when promoting a trained model from experimentation to production, managing multiple model versions across development stages, implementing approval workflows for governance, rolling back to previous versions, or auditing model changes for compliance.

日本語の概要は準備中です。原文の説明を表示しています。

Orchestrate end-to-end machine learning pipelines using Prefect or Airflow with DAG construction, task dependencies, retry logic, scheduling, monitoring, and integration with MLflow, DVC, and feature stores for production ML workflows. Use when automating multi-step ML workflows from data ingestion to deployment, scheduling periodic model retraining, coordinating distributed training tasks, or managing retry logic and failure recovery across pipeline stages.

日本語の概要は準備中です。原文の説明を表示しています。

Deploy machine learning models to edge devices using Google AI Edge Gallery, TensorFlow Lite, ONNX Runtime, and MediaPipe. Covers model quantization (INT8/INT4), on-device inference with Gemma 4 models, Android/iOS deployment via AI Edge Gallery, hardware delegate selection (GPU/NPU/DSP), and performance benchmarking on constrained devices. Use when deploying models to mobile phones, IoT devices, or embedded systems where cloud inference is impractical due to latency, cost, or connectivity constraints.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze pre-trained generative diffusion models (Stable Diffusion, DALL-E, Flux) by computing quality metrics (FID, IS, CLIP score, precision/recall), inspecting noise schedules, extracting and visualizing attention maps, and probing latent spaces. Use when evaluating a pre-trained generative diffusion model's output quality, comparing noise schedule variants, analyzing cross-attention patterns for text-conditioned generation, interpolating between latent codes, or detecting out-of-distribution inputs.

日本語の概要は準備中です。原文の説明を表示しています。

Composer conventions for any PHP project: dependency management, version constraints, PSR-4 autoloading, scripts, platform requirements, and the composer.json vs composer.lock contract. Stack-agnostic — referenced by every PHP plugin in the marketplace. Use this skill to: - Read composer.json to detect the PHP version, framework, and key packages before writing code. - Add dependencies with correct version constraints and the right require vs require-dev placement. - Configure PSR-4 autoloading and regenerate the autoloader after adding namespaces. - Use composer scripts and platform config consistently. Do NOT use this skill for: - PHP language idioms — see php-foundation:php-conventions. - Testing setup and runners — see php-foundation:php-testing. - Framework-specific package guidance (Laravel/Symfony bundles) — those live in framework plugin skills.

日本語の概要は準備中です。原文の説明を表示しています。

Django ORM patterns: model definitions, field types, model managers, custom QuerySet methods, select_related/prefetch_related for N+1 prevention, transactions, F/Q expressions, Meta indexes and constraints. For django-architect (model definitions) and django-migrations-specialist (field finalization). Activated automatically by django-plugin/stack.md. Use this skill to: - Write clean, efficient Django model definitions with proper field choices and __str__. - Use custom managers and QuerySets to encapsulate query logic. - Prevent N+1 queries with select_related and prefetch_related. - Use transactions for atomic operations. - Define Meta indexes and constraints (for django-migrations-specialist to finalize). Do NOT use this skill for: - Creating actual migrations (makemigrations) — that is django-migrations-specialist. - Web view / API patterns — see django-plugin:django-conventions. - Python idioms — see python-foundation:python-conventions.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive primary skill for agents working with Weights & Biases. Covers both the W&B SDK (training runs, metrics, artifacts, sweeps) and the Weave SDK (GenAI traces, evaluations, scorers). Includes helper libraries, gotcha tables, and data analysis patterns. Use this skill whenever the user asks about W&B runs, Weave traces, evaluations, training metrics, loss curves, model comparisons, or any Weights & Biases data — even if they don't say "W&B" explicitly.

日本語の概要は準備中です。原文の説明を表示しています。

应用从 AI for Everyone 蒸馏出的「训练集/测试集分离 — AI的'科学方法」方法论。Use when the user needs practical guidance, diagnosis, workflow design, decision support, or an action plan related to train-test-split.

日本語の概要は準備中です。原文の説明を表示しています。

应用从 AI for Everyone 蒸馏出的「分层AI培训 — 高管/经理/工程师的差异化学习」方法论。Use when the user needs practical guidance, diagnosis, workflow design, decision support, or an action plan related to role-tiered-training.

日本語の概要は準備中です。原文の説明を表示しています。

Use when any bounded workflow starts or reaches an action, path, proposal, or merge boundary. Refuses rather than default-allow on an unreadable constraint set.

日本語の概要は準備中です。原文の説明を表示しています。

Use when asked to implement under non-negotiable constraints: performance budgets, platform limits, legal or API rules. Not for remote, credential, publish, deploy, or irreversible changes.

日本語の概要は準備中です。原文の説明を表示しています。

Adapt torch_npu.profiler interface for AI frameworks and training/inference code on Ascend NPU. Use this skill whenever users need to integrate profiling, add performance data collection, or instrument PyTorch code with torch_npu.profiler on Huawei Ascend NPU platforms. Triggers on: "torch_npu profiler", "NPU profiling", "Ascend profiler", "profiler adaptation", "profile training", "profile inference", "add profiler to framework", "性能采集", "profiling 数据", "昇腾 profiler", and any request to add performance monitoring to Ascend NPU code.

日本語の概要は準備中です。原文の説明を表示しています。

RL 强化学习训练与推理（rollout）路径的算子差异性扫描。当用户提供训练启动脚本路径，要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异（尤其是融合算子 vs 单算子不一致）时使用此 skill。典型触发词包括"训推算子扫描"、"训推差异性"、"算子差异报告"、"融合算子对比"、"train vs infer op diff"。注意：本 skill 通过运行完整 RL 训练脚本（集成 profiling）来采集真实运行时算子（非静态源码扫描，非独立分离运行）。当训练、推理使用不同脚本时禁止触发。

日本語の概要は準備中です。原文の説明を表示しています。

Design reliable, safe, and trustworthy agent systems that fail gracefully and operate within bounds. Use when building guardrails, handling edge cases, preventing harmful outputs, monitoring for failures, implementing safety constraints, or designing error recovery. Covers failure modes, constraint systems, oversight mechanisms, and safety validation.

日本語の概要は準備中です。原文の説明を表示しています。

Build and validate Azure infrastructure in a lab or sandbox using Azure CLI and official Microsoft docs. Use when creating verification environments, provisioning hub-and-spoke VNets, VPN Gateway or ExpressRoute-adjacent validation labs, checking subscription/tenant access, debugging Azure deployment constraints, comparing before/after route behavior, or cleaning up lab resources. Triggers on 'Azure 検証', '検証環境', 'PoC', 'sandbox', 'lab', 'Azure CLI で構築', 'VPN Gateway', 'VNet peering', 'BGP', 'route validation', 'summarizedGatewayPrefixes', 'デプロイして検証', 'インフラ検証'.

"Apply the Born Global framework to analyze firms that internationalize rapidly from inception under resource constraints. Use this skill when the user needs to evaluate whether a startup or SME can pursue early internationalization, identify the capabilities enabling born globals, or design a resource-constrained international market entry strategy.".

日本語の概要は準備中です。原文の説明を表示しています。

Ask the minimum clarifying questions before implementing when scope, constraints, or success criteria are unclear. Use when a request has multiple plausible interpretations, missing acceptance criteria, or ambiguous environment constraints.

日本語の概要は準備中です。原文の説明を表示しています。

"Apply Theory of Constraints (TOC) to identify and manage system bottlenecks. Use this skill when the user needs to find what limits throughput, optimize a constrained process, apply the Five Focusing Steps, or implement Drum-Buffer-Rope scheduling — even if they say 'our output is stuck', 'what's the bottleneck', or 'why can't we produce more'.".

日本語の概要は準備中です。原文の説明を表示しています。